Azure / Azure/MachineLearningNotebooks

monitor.backfill() in datadrift tutorial is quite time consuming

Open
#1,653 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
4.4k
Forks
2.6k
PR merge metrics
No merged PRs in 30d

Description

Hello Microsoft Team,

I am studying datadrift monitoring and following [Azure datadrift tutorial](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/work-with-data/datadrift-tutorial/datadrift-tutorial.ipynb) but when I go to `monitor.backfill()` step, it is quite time consuming to execute.

```
from azureml.widgets import RunDetails

backfill = monitor.backfill(dt.datetime.now() - dt.timedelta(weeks=6), dt.datetime.now())

RunDetails(backfill).show()
backfill.wait_for_completion()
```

As you can see in the capture picture. It have been wasting me up to 9h but have not yet completed. My baseline and target data keep the same as example and I run on compute instance with configuration:

```
Virtual machine size
Standard_DS11_v2 (4 cores, 14 GB RAM, 28 GB disk)
```
Can you explain what error happen with this example tutorial?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.